Segmentation of Periventricular White Matter in Neonatal Brain MRI: Analysis of Brain Maturation in Term and Preterm Cohorts

AbstractMRI is conventionally employed in neonatal brain diagnosis and research studies. However, the traditional segmentation protocols omit differentiation between heterogeneous white matter (WM) tissue zones that rapidly evolve change during early development. There a reported correlations of characteristics transient WM compartments (including periventricular regions, subplate, etc.) with maturation [23, 26] neurodevelopment scores [22]. there are no currently available standards for parcellation these regions MRI scans. Therefore, this work, we propose first deep learning solution automated 3D (PWM) would be step towards tissue-specific analysis. The implemented method based on UNETR [13] was then used assessment differences term preterm cohorts (200 subjects) from developing Human Connectome Project (dHCP) project [1] terms ROI-specific volumetry microstructural diffusion indices.KeywordsNeonatal MRIPeriventricular matterBrain maturationAutomated